{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:LLIKK4AMOAZL5CBHBFV4NQKN3J","short_pith_number":"pith:LLIKK4AM","canonical_record":{"source":{"id":"2110.03177","kind":"arxiv","version":8},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-07T04:12:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fd30c572d0ea8ed64afe7858bcc599afd6033be8ab0b59df947a1ec303999e88","abstract_canon_sha256":"5ed6351d442c68561205bd00a5b60fc3ba992865ed17f07818023467c2f6c981"},"schema_version":"1.0"},"canonical_sha256":"5ad0a5700c7032be8827096bc6c14dda686d1d82ddfbc97f3ff733432a096ad9","source":{"kind":"arxiv","id":"2110.03177","version":8},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03177","created_at":"2026-07-05T04:22:52Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03177v8","created_at":"2026-07-05T04:22:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03177","created_at":"2026-07-05T04:22:52Z"},{"alias_kind":"pith_short_12","alias_value":"LLIKK4AMOAZL","created_at":"2026-07-05T04:22:52Z"},{"alias_kind":"pith_short_16","alias_value":"LLIKK4AMOAZL5CBH","created_at":"2026-07-05T04:22:52Z"},{"alias_kind":"pith_short_8","alias_value":"LLIKK4AM","created_at":"2026-07-05T04:22:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:LLIKK4AMOAZL5CBHBFV4NQKN3J","target":"record","payload":{"canonical_record":{"source":{"id":"2110.03177","kind":"arxiv","version":8},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-07T04:12:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fd30c572d0ea8ed64afe7858bcc599afd6033be8ab0b59df947a1ec303999e88","abstract_canon_sha256":"5ed6351d442c68561205bd00a5b60fc3ba992865ed17f07818023467c2f6c981"},"schema_version":"1.0"},"canonical_sha256":"5ad0a5700c7032be8827096bc6c14dda686d1d82ddfbc97f3ff733432a096ad9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:52.591926Z","signature_b64":"wSiapqp1Zb2/BOoasvQO+XWvApZfg42DMOdsYeoOSkHTX13xh3b9NzuZh0inbHt0jDPnY0HGTYU4WJ8EcA4GAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ad0a5700c7032be8827096bc6c14dda686d1d82ddfbc97f3ff733432a096ad9","last_reissued_at":"2026-07-05T04:22:52.591439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:52.591439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.03177","source_version":8,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:22:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ea0SHflaNZ1bzLFBYEaVJA7h1A2s+kYtgGUxbQNwfoC4AzrBGW2Q+fDFcx9DQxN3EMm2JCHTZVLkxpqK71WqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:58:12.969786Z"},"content_sha256":"35f463343c5e08e3dcb3c576cae3ff33b3824a88fae51f1db5ac8e46ab39fd54","schema_version":"1.0","event_id":"sha256:35f463343c5e08e3dcb3c576cae3ff33b3824a88fae51f1db5ac8e46ab39fd54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:LLIKK4AMOAZL5CBHBFV4NQKN3J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arindam Banerjee, Jingrui He, Yikun Ban, Yuchen Yan","submitted_at":"2021-10-07T04:12:36Z","abstract_excerpt":"In this paper, we propose a novel neural exploration strategy in contextual bandits, EE-Net, distinct from the standard UCB-based and TS-based approaches. Contextual multi-armed bandits have been studied for decades with various applications. To solve the exploitation-exploration tradeoff in bandits, there are three main techniques: epsilon-greedy, Thompson Sampling (TS), and Upper Confidence Bound (UCB). In recent literature, linear contextual bandits have adopted ridge regression to estimate the reward function and combine it with TS or UCB strategies for exploration. However, this line of w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03177","kind":"arxiv","version":8},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.03177/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:22:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c/QMZ7EQgER3BiVKOi9SH7VD5n9A+vviPbHhGRKpCveeHZyFj2xR5RpADvK1+7PUGs0iShSLA6QmX3EppCjjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:58:12.970273Z"},"content_sha256":"dd0ee23121769ce5eb01b5e3329d2d74f6cce9b9662203e0f38d28521f51eaf5","schema_version":"1.0","event_id":"sha256:dd0ee23121769ce5eb01b5e3329d2d74f6cce9b9662203e0f38d28521f51eaf5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LLIKK4AMOAZL5CBHBFV4NQKN3J/bundle.json","state_url":"https://pith.science/pith/LLIKK4AMOAZL5CBHBFV4NQKN3J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LLIKK4AMOAZL5CBHBFV4NQKN3J/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T01:58:12Z","links":{"resolver":"https://pith.science/pith/LLIKK4AMOAZL5CBHBFV4NQKN3J","bundle":"https://pith.science/pith/LLIKK4AMOAZL5CBHBFV4NQKN3J/bundle.json","state":"https://pith.science/pith/LLIKK4AMOAZL5CBHBFV4NQKN3J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LLIKK4AMOAZL5CBHBFV4NQKN3J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LLIKK4AMOAZL5CBHBFV4NQKN3J","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5ed6351d442c68561205bd00a5b60fc3ba992865ed17f07818023467c2f6c981","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-07T04:12:36Z","title_canon_sha256":"fd30c572d0ea8ed64afe7858bcc599afd6033be8ab0b59df947a1ec303999e88"},"schema_version":"1.0","source":{"id":"2110.03177","kind":"arxiv","version":8}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03177","created_at":"2026-07-05T04:22:52Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03177v8","created_at":"2026-07-05T04:22:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03177","created_at":"2026-07-05T04:22:52Z"},{"alias_kind":"pith_short_12","alias_value":"LLIKK4AMOAZL","created_at":"2026-07-05T04:22:52Z"},{"alias_kind":"pith_short_16","alias_value":"LLIKK4AMOAZL5CBH","created_at":"2026-07-05T04:22:52Z"},{"alias_kind":"pith_short_8","alias_value":"LLIKK4AM","created_at":"2026-07-05T04:22:52Z"}],"graph_snapshots":[{"event_id":"sha256:dd0ee23121769ce5eb01b5e3329d2d74f6cce9b9662203e0f38d28521f51eaf5","target":"graph","created_at":"2026-07-05T04:22:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2110.03177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel neural exploration strategy in contextual bandits, EE-Net, distinct from the standard UCB-based and TS-based approaches. Contextual multi-armed bandits have been studied for decades with various applications. To solve the exploitation-exploration tradeoff in bandits, there are three main techniques: epsilon-greedy, Thompson Sampling (TS), and Upper Confidence Bound (UCB). In recent literature, linear contextual bandits have adopted ridge regression to estimate the reward function and combine it with TS or UCB strategies for exploration. However, this line of w","authors_text":"Arindam Banerjee, Jingrui He, Yikun Ban, Yuchen Yan","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-07T04:12:36Z","title":"EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03177","kind":"arxiv","version":8},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:35f463343c5e08e3dcb3c576cae3ff33b3824a88fae51f1db5ac8e46ab39fd54","target":"record","created_at":"2026-07-05T04:22:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5ed6351d442c68561205bd00a5b60fc3ba992865ed17f07818023467c2f6c981","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-07T04:12:36Z","title_canon_sha256":"fd30c572d0ea8ed64afe7858bcc599afd6033be8ab0b59df947a1ec303999e88"},"schema_version":"1.0","source":{"id":"2110.03177","kind":"arxiv","version":8}},"canonical_sha256":"5ad0a5700c7032be8827096bc6c14dda686d1d82ddfbc97f3ff733432a096ad9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ad0a5700c7032be8827096bc6c14dda686d1d82ddfbc97f3ff733432a096ad9","first_computed_at":"2026-07-05T04:22:52.591439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:52.591439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wSiapqp1Zb2/BOoasvQO+XWvApZfg42DMOdsYeoOSkHTX13xh3b9NzuZh0inbHt0jDPnY0HGTYU4WJ8EcA4GAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:52.591926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.03177","source_kind":"arxiv","source_version":8}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35f463343c5e08e3dcb3c576cae3ff33b3824a88fae51f1db5ac8e46ab39fd54","sha256:dd0ee23121769ce5eb01b5e3329d2d74f6cce9b9662203e0f38d28521f51eaf5"],"state_sha256":"4e9c4016ebfb0ace6da65fb8314abb2eeebbe13c62d7829217353f2dab7ddfb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tLwrTtDVo3qzhiUKyNPwi6VAMBMI91LhFEW0ff1p/ZWy8tnXmcWUVtwe0MdIV8HDA+ykZuAwD+iuWSVbpN5NBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T01:58:12.975520Z","bundle_sha256":"b058121d0d1519854b362559f9a0f2a5d0150312a6e527e64dc901fdd6ba9f53"}}